He slammed the door, the sound echoing through the empty apartment. His jaw was clenched, his shoulders rigid. He’d been working on a screenplay for weeks. Then, a crushing rejection email. He’d just sent a text to his agent: “This town is a joke. I’m done.” He meant to text his friend, Mark, but a fat finger had instead selected his grandmother’s number. He groaned, scrubbing a hand over his face. He quickly retyped a different message for Mark, a rant about the email, and then he texted his grandmother an apology. He didn't want to explain his foul mood to her.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

This story is one of 1,000 stories generated for the emotion upset. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 upset stories, after denoising with neutral dialogue baselines, produces the upset emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the upset vector is projected through the unembedding matrix.

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210